WO2019047487A1 - 基于声纹识别的坐席登录方法、电子装置及存储介质 - Google Patents

基于声纹识别的坐席登录方法、电子装置及存储介质 Download PDF

Info

Publication number
WO2019047487A1
WO2019047487A1 PCT/CN2018/077375 CN2018077375W WO2019047487A1 WO 2019047487 A1 WO2019047487 A1 WO 2019047487A1 CN 2018077375 W CN2018077375 W CN 2018077375W WO 2019047487 A1 WO2019047487 A1 WO 2019047487A1
Authority
WO
WIPO (PCT)
Prior art keywords
agent
information
voiceprint
registered
identity
Prior art date
Application number
PCT/CN2018/077375
Other languages
English (en)
French (fr)
Inventor
邱贝
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Priority to SG11201811498QA priority Critical patent/SG11201811498QA/en
Priority to US16/338,957 priority patent/US20210312023A1/en
Priority to JP2018561019A priority patent/JP2019535025A/ja
Publication of WO2019047487A1 publication Critical patent/WO2019047487A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
    • H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/36—User authentication by graphic or iconic representation
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/06—Decision making techniques; Pattern matching strategies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
    • H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
    • H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
    • H04L9/3231—Biological data, e.g. fingerprint, voice or retina
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/12—Messaging; Mailboxes; Announcements

Definitions

  • the present application relates to the field of login authentication technology, and relates to a method for registering an agent based on voiceprint recognition, an electronic device, and a storage medium.
  • the technical problem to be solved by the present application is to overcome the problem of poor security of the business system login in the prior art, and to propose a method for registering an agent based on voiceprint recognition, an electronic device and a storage medium, through the seat identity and voiceprint
  • the two-factor authentication method ensures the security of the business system login, and thus ensures the information security of the enterprise.
  • An agent registration method based on voiceprint recognition includes the following steps: S1: receiving login request information initiated by an agent, where the login request information includes unique identification information identifying an agent identity; S2, and verifying by using the unique identification information Whether the agent is a registered agent, if yes, executing step S3; S3, randomly generating identity review information is provided to the agent, and prompting the agent to read the identity review information by using a uniform speed verbatim color change; S4, receiving the The agent reads the voice information of the identity review information; S5, performing voiceprint registration verification on the agent according to the received voice information, and returning the verification result.
  • An electronic device includes a memory and a processor, wherein the memory stores a voiceprint recognition-based agent registration system executable by the processor, and the voiceprint recognition-based agent registration system includes: an identity input module, And an identity verification module, configured to verify, according to the unique identification information, whether the agent is a registered agent, and return a verification result; a random information generating module, After the identity verification is passed, the identity review information is randomly generated and displayed; the follow-up prompting module is configured to change the displayed identity review information by word-by-word to prompt the agent to read the identity review at a constant speed.
  • the information input module is configured to receive the sound information of the identity review information by the agent; the voiceprint comparison module is configured to perform voiceprint registration verification on the agent according to the sound information, and return a verification result.
  • a computer readable storage medium having stored therein a voiceprint recognition based agent registration system, the voiceprint recognition based agent registration system being executable by at least one processor to cause the The at least one processor performs the following steps: S1: receiving agent-initiated login request information, where the login request information includes unique identification information identifying the agent identity; S2, verifying, by the unique identification information, whether the agent is a registered agent If yes, step S3 is performed; S3, randomly generating identity review information is provided to the agent, and the agent is prompted to read the identity review information by using a uniform speed word-by-word color change; S4, receiving the agent to read the identity review information The voice information is obtained; S5, performing voiceprint registration verification on the agent according to the received voice information, and returning the verification result.
  • the positive progress of the application is that the application ensures the security of the login of the business system through the login method of the identity of the agent and the dual verification of the voiceprint; at the same time, the function of ensuring the agent is ensured by adding the function of the speed-changing word-by-word color change. Each time you enter, you can follow the speed as much as possible to improve the accuracy of voiceprint verification.
  • FIG. 1 is a schematic diagram showing the hardware architecture of an embodiment of an electronic device of the present application.
  • FIG. 2 is a schematic diagram showing a program module of a first embodiment of a voice registration based seat registration system in an electronic device of the present application
  • FIG. 3 is a schematic diagram of a program module of a second embodiment of a voice registration based agent registration system in an electronic device of the present application;
  • FIG. 4 is a schematic diagram showing a program module of the identity verification module in the third embodiment of the voiceprint recognition based agent registration system in the electronic device of the present application;
  • FIG. 5 is a schematic diagram showing a program module of the voiceprint comparison module in the fourth embodiment of the voiceprint recognition based agent registration system in the electronic device of the present application;
  • FIG. 6 is a flow chart showing an embodiment of a method for registering an agent based on voiceprint recognition according to the present application
  • FIG. 7 is a flow chart showing another embodiment of a method for registering an agent based on voiceprint recognition according to the present application.
  • FIG. 8 is a flowchart showing the construction of a registered agent information base in still another embodiment of the voice registration-based agent registration method according to the present application.
  • FIG. 9 is a flow chart showing the construction of a registered agent information base in a further embodiment of the voiceprint recognition based agent registration method of the present application.
  • the present application proposes an electronic device.
  • the electronic device 1 is an apparatus capable of automatically performing numerical calculation and/or information processing in accordance with an instruction set or stored in advance.
  • the electronic device 2 can be a smartphone, a tablet, a laptop, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including a stand-alone server, or a server cluster composed of multiple servers).
  • the electronic device 2 includes at least, but not limited to, a memory 21, a processor 22, a network interface 23, and a voiceprint recognition based agent registration system 20 that are communicably coupled to each other through a system bus. among them:
  • the memory 21 includes at least one type of computer readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), Static Random Access Memory (SRAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • the memory 21 may be an internal storage unit of the electronic device 2, such as a hard disk or a memory of the electronic device 2.
  • the memory 21 may also be an external storage device of the electronic device 2, such as a plug-in hard disk equipped on the electronic device 2, a smart memory card (SMC), and a secure digital device. (Secure Digital, SD) card, flash card, etc.
  • the memory 21 can also include both the internal storage unit of the electronic device 2 and its external storage device.
  • the memory 21 is generally used to store an operating system installed in the electronic device 2 and various types of application software, such as the program code of the voiceprint recognition-based agent registration system 20, and the like. Further, the memory 21 can also be used to temporarily store various types of data that have been output or are to be output.
  • the processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 22 is typically used to control the overall operation of the electronic device 2, such as performing control and processing associated with data interaction or communication with the electronic device 2.
  • the processor 22 is configured to run program code or processing data stored in the memory 21, such as running the voiceprint recognition based agent registration system 20 and the like.
  • the network interface 23 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the electronic device 2 and other electronic devices.
  • the network interface 23 is configured to connect the electronic device 2 to an external terminal through a network, establish a data transmission channel, a communication connection, and the like between the electronic device 2 and an external terminal.
  • the network may be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, or a 5G network.
  • Wireless or wired networks such as network, Bluetooth, Wi-Fi, etc.
  • FIG. 1 only shows the electronic device 2 with the components 21-23, but it should be understood that not all illustrated components are required to be implemented, and more or fewer components may be implemented instead.
  • the voiceprint recognition-based agent registration system 20 stored in the memory 21 may be divided into one or more program modules, and the one or more program modules are stored in the memory 21, and It can be performed by one or more processors (the processor 22 in this embodiment) to complete the application.
  • FIG. 2 shows a schematic diagram of a program module of the first embodiment of the voiceprint recognition based agent registration system 20.
  • the voiceprint recognition based agent registration system 20 can be divided into an identity input module. 201.
  • the following description will specifically describe the specific functions of the program modules 201-206.
  • the identity input module 201 is configured to receive login request information of an agent that includes unique identification information that identifies an agent identity;
  • the identity verification module 202 is configured to verify, according to the unique identification information, whether the agent is a registered agent, and return a verification result;
  • the random information generating module 203 is configured to randomly generate and display the identity review information after the identity verification is passed;
  • the follow-up prompting module 204 is configured to change the displayed identity review information by word-by-word to prompt the agent to read the identity review information at an average speed;
  • the sound input module 205 is configured to receive sound information that the agent reads the identity review information
  • the voiceprint comparison module 206 is configured to perform voiceprint registration verification on the agent according to the sound information, and return a verification result.
  • voiceprint recognition based agent registration system 20 facilitates orderly management of the agent.
  • the following uses the system to log in to the agent system to specify:
  • the first step is to enter the agent login system.
  • the first login page is popped up to input the unique identification information of the agent.
  • the unique identification information here can be the work number of the agent.
  • the following steps are all based on the work number. Description: After receiving the job number, the system sends the job number and the information and other information inherent to the station to the login request information.
  • the work number included in the login request information determine whether the agent represented by the work number is a registered agent; specifically, determine whether the work number is the same as one of the work numbers preset by the registered agent information database; The registered agent information database finds the same preset work number as the work number, and returns the comparison result representing the agent as the registered agent; otherwise, the login is ended.
  • the second login page is popped up, and the second login page displays a randomly generated list of identity review information, which may be a string of numbers, letters, characters or three kinds of arbitrary combination.
  • the agent reads out a series of identity review information according to the uniform speed word-by-word color change prompt, and simultaneously records the voice information of the agent and the reader.
  • FIG. 3 shows a schematic diagram of a program module of the second embodiment of the voiceprint recognition based agent registration system 20.
  • the voiceprint recognition based agent registration system 20 can also be divided into an identity.
  • the check code generating module 207 is configured to: after the voiceprint login verification fails, randomly generate a check code and send the check code to the preset mailbox or the mobile phone end of the agent;
  • the check code input module 208 is configured to receive a check code input by the agent
  • the check code verification module 209 is configured to check the received check code and return a check result.
  • agent uses the system to log in to the agent system after failure:
  • the system automatically generates a random check code and sends it to the mailbox or mobile phone that is preset in the registered agent information database and associated with the agent number of the agent.
  • the agent inputs the received check code, and the system compares the received check code with the check code sent to the agent. If the check code is completely consistent, the check code verification is passed, and the agent is allowed to enter the service system to continue operation. If the check code received by the system and the check code sent to the agent have any one of the check codes, it means that the check code verification fails, and the login is ended.
  • FIG. 4 is a schematic diagram of a program module of the identity verification module 202 in the third embodiment of the voiceprint recognition based agent registration system.
  • the voiceprint recognition based agent registration system 20 is Based on the foregoing second embodiment, the identity verification module 202 is further divided into an information intercepting sub-module 2021 and an identity identifying sub-module 2022.
  • the information intercepting sub-module 21 is configured to intercept the unique identification information included in the login request information
  • the identity recognition sub-module 22 is configured to compare the unique identification information with the agent information preset in the registered agent information database, and return the comparison result.
  • FIG. 5 is a schematic diagram of a program module of the voiceprint comparison module 206 in the third embodiment of the voiceprint recognition based agent registration system.
  • the voiceprint recognition based agent registration system is used.
  • the voiceprint matching module 206 is further divided into a voiceprint extraction sub-module 2061, a voiceprint calling sub-module 2062, and a voiceprint comparison sub-module 2063.
  • the voiceprint extraction sub-module 2061 is configured to extract voiceprint information from the sound information
  • the voiceprint calling sub-module 2062 is configured to search for a voiceprint sample associated with the same agent information from the registered agent information database and call it out;
  • the voiceprint comparison sub-module 2063 is configured to compare the voiceprint information with the called voiceprint sample, and return a comparison result.
  • the present application proposes an agent registration method based on voiceprint recognition.
  • the voiceprint recognition based agent registration method includes the following steps:
  • S1 Receive login request information initiated by the agent, where the login request information includes unique identification information identifying the identity of the agent.
  • the voice registration-based agent registration method in the embodiment of the present application is applied to the service login system.
  • the agent opens the service system to prepare for login
  • the account needs to be input at the agent end of the service system, and the account is converted into a login request.
  • the information is sent to the business login system.
  • the partial information of the fixed location in the converted login request information is unique identification information for identifying the identity of the agent.
  • the fifth bit of the login request information is The 10th digit string is unique identification information.
  • step S2 Verify, by the unique identification information, whether the agent is a registered agent, and if yes, execute step S3.
  • verifying whether it is a registered agent may include the following steps:
  • the preceding character string representing the unique identification information having a length of 6 bits is compared with the seat information preset in the registered agent information database, wherein the length of the agent information is consistent with the length of the unique identification information.
  • the unique identification information is a character string of length 6 bits, and thus the length of the agent information is necessarily assumed to be 6 bits.
  • step S3 is verified and executed.
  • Step S3 is executed only when the comparison result is 1, and the login is ended when the comparison result is 0.
  • the agent authentication is passed, that is, the agent is the registered agent of the business system, and has the right to use the business system, but also needs to perform login verification through voiceprint recognition.
  • the agent authentication is passed, it is possible that the agent actually logging into the business system is a non-registered agent, but the non-registered agent obtains a valid account of the registered agent through an unreasonable channel, if directly verified by entering a password. Logging in to the service system may cause enterprise information to be leaked. Therefore, after verifying that the agent being logged in is a registered agent, the system randomly generates identity review information to be provided to the agent for login verification of the agent.
  • the identity review information may be a number of words, a number, or a random combination of the numbers of words and numbers.
  • the identity review information may be several Chinese characters, such as "Welcome to the login business system", or several numbers, such as "23059487", or a combination of several Chinese characters and several numbers. For example, "Good morning 5768".
  • the characters described herein are not limited to Chinese characters, and may be English letters or the like.
  • the system automatically causes the identity review information to be changed word by word at an average speed of a certain speed, so as to prompt the agent to read the identity review information verbatim at a speed of color change.
  • the start time of the verbatim color change can also be designed to be controlled by the agent himself. For example, near the position where the identity review information is displayed, the start button is added. After the agent is ready, after clicking the start button, the identity review information starts to change character by word. .
  • the end time of receiving the voice information can be preset in the system due to the use of the word-by-word color-changing prompt, for example, the voice information is received by default after 3 seconds of the color change of the last word of the identity review information. Automatically stop receiving voice messages.
  • the end of receiving the voice message can also be determined by the agent himself, as long as the start button is the same as the start button.
  • the voiceprint login verification has the following steps:
  • the voiceprint information in particular, can characterize a person's characteristics, and thus the voiceprint information extracted herein is a feature that extracts the characteristics of the seat that can characterize the reading of the identity review information from the received voice information. .
  • the voiceprint sample described herein refers to the voiceprint information of the registered agent preset in the registered agent information base, and a voiceprint sample is associated with a unique agent information and stored in the registered agent information base.
  • the currently acquired voiceprint information is matched with a voiceprint sample belonging to the voiceprint information unique to the agent identity represented by the same agent information as the unique identification information.
  • the voiceprint sample that is called belongs to the agent identity represented by the same agent information as the unique identification information; therefore, when the voiceprint information matches the voiceprint sample that is called, It is determined that the agent of the current login service system is indeed the agent represented by the unique identification information, and then the login verification is performed to allow the agent to enter the business system to continue the operation.
  • the voiceprint recognition-based agent registration method includes, according to the foregoing method, a verification code registration verification step after the voiceprint login verification fails, and the specific steps are performed. as follows:
  • the voiceprint verification Since each time by recognizing the voiceprint information in the recording to identify the personal identity information has a certain error, the error comes from the recording environment or the change of the individual's own voice, etc., so the voiceprint verification does not require voiceprint information. And the soundprint sample is completely matched, usually only a certain degree of matching is reached; moreover, when the matching degree does not reach the preset value, the currently registered agent may also be the same as the unique identification information. The agent represented by the agent information. Therefore, after the voiceprint login verification fails, the abnormality of the voiceprint login verification may be compensated by adding the verification code login verification.
  • Checksum Login Verification is a supplement to Voiceprint Login Verification and will only be initiated after entering the Voiceprint Login Verification Step and the verification fails.
  • the information associated with the agent information in the registered agent information database is associated with the mobile phone number or the mailbox of the registered agent or both, in addition to the voiceprint sample.
  • the voiceprint login verification step it means that the agent has been confirmed as the registered agent by the unique identification information.
  • the check code is randomly generated and sent to the same agent information as the unique identification information. Associated with a mailbox or phone.
  • the timing of randomly generating the check code may be after the voiceprint login verification fails once, or may be set to three times after the voiceprint login verification fails, that is, the opportunity for the voiceprint verification is given three times.
  • the generation of the check code can also be controlled by the agent, and the agent selects whether it is necessary to generate and send a check code.
  • the verification is passed, allowing the agent to enter the service system to continue the operation; otherwise, the login is ended.
  • the voiceprint recognition-based agent registration method further includes the method of registering the agent information database before entering the login verification, based on the method described in the foregoing embodiment. Steps, the specific steps are as follows:
  • S01 Receive unique identification information of the agent to be registered, and temporarily store the unique identification information as the agent information of the agent to be registered;
  • the at least one of the to-be-registered agents reads the following information at least three times, and temporarily stores the plurality of follow-up voice information of the to-be-registered agent;
  • S06 Associate the voiceprint sample with the temporarily stored agent information of the to-be-registered agent.
  • the voice registration method of the agent registration method also includes the association of the agent information with the mobile phone number and/or the mailbox when the registration agent database is constructed. The specific steps are as follows:
  • the present application is a computer readable storage medium having stored therein a voiceprint recognition based agent registration system 20 that can be executed by one or more processors At the time, the above-described voice registration-based agent registration method or operation of the electronic device is implemented.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Collating Specific Patterns (AREA)
  • Telephonic Communication Services (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

本申请公开了一种基于声纹识别的坐席登录方法，属于登录认证技术领域。一种基于声纹识别的坐席登录方法，包括如下步骤：S1、接收坐席发起的登录请求信息，所述登录请求信息中包含有识别坐席身份的唯一识别信息；S2、通过所述唯一识别信息验证所述坐席是否为注册坐席，若是则执行步骤 S3；S3、随机生成身份复核信息提供至所述坐席，并通过均速逐字变色提示所述坐席阅读所述身份复核信息；S4、接收所述坐席阅读所述身份复核信息的语音信息；S5、根据接收到的所述语音信息对所述坐席进行声纹登录验证。本申请提供了坐席身份和声纹双重验证的登录方法并加入了均速逐字变色提示跟读功能，以确保业务系统登录的安全性和验证的准确性。

Description

基于声纹识别的坐席登录方法、电子装置及存储介质
本申请申明享有2017年9月11日递交的申请号为201710814313.4、名称为“基于声纹识别的坐席登录方法、电子装置及存储介质”的中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及登录认证技术领域，涉及一种基于声纹识别的坐席登录方法、电子装置及存储介质。
背景技术
现有的业务系统，只要获取一个有效的坐席人员的账号和密码便可以登录系统，无法识别是否是该坐席人员本人登录。一旦非坐席人员从不合理的渠道获得一个坐席人员的有效账号和密码后登录业务系统，很容易造成信息泄露，严重威胁企业信息安全，并且在信息泄露后很难追查。
因此，如何进一步提高业务系统登录的安全性和可靠性，并保护企业信息安全成为亟待解决的技术问题。
发明内容
本申请要解决的技术问题是为了克服现有技术中业务系统登录的安全性不佳的问题，提出了一种基于声纹识别的坐席登录方法、电子装置及存储介质，通过坐席身份和声纹双重验证的方式，确保了业务系统登录的安全性，进而得以保证企业的信息安全。
本申请是通过下述技术方案来解决上述技术问题：
一种基于声纹识别的坐席登录方法，包括如下步骤：S1、接收坐席发起的登录请求信息，所述登录请求信息中包含有识别坐席身份的唯一识别信 息；S2、通过所述唯一识别信息验证所述坐席是否为注册坐席，若是则执行步骤S3；S3、随机生成身份复核信息提供至所述坐席，并通过均速逐字变色提示所述坐席阅读所述身份复核信息；S4、接收所述坐席阅读所述身份复核信息的语音信息；S5、根据接收到的所述语音信息对所述坐席进行声纹登录验证，并返回验证结果。
一种电子装置，包括存储器和处理器，所述存储器上存储有可被所述处理器执行的基于声纹识别的坐席登录系统，所述基于声纹识别的坐席登录系统包括：身份输入模块，用于接收包含有识别坐席身份的唯一识别信息的坐席的登录请求信息；身份验证模块，用于根据所述唯一识别信息验证所述坐席是否为注册坐席，并返回验证结果；随机信息生成模块，用于在身份验证通过后，随机生成身份复核信息并显示；跟读提示模块，用于使显示的所述身份复核信息均速逐字变色，以提示所述坐席以均速阅读所述身份复核信息；声音输入模块，用于接收所述坐席阅读所述身份复核信息的声音信息；声纹比对模块，用于根据所述声音信息对所述坐席进行声纹登录验证，并返回验证结果。
一种计算机可读存储介质，所述计算机可读存储介质内存储有基于声纹识别的坐席登录系统，所述基于声纹识别的坐席登录系统可被至少一个处理器所执行，以使所述至少一个处理器执行以下步骤：S1、接收坐席发起的登录请求信息，所述登录请求信息中包含有识别坐席身份的唯一识别信息；S2、通过所述唯一识别信息验证所述坐席是否为注册坐席，若是则执行步骤S3；S3、随机生成身份复核信息提供至所述坐席，并通过均速逐字变色提示所述坐席阅读所述身份复核信息；S4、接收所述坐席阅读所述身份复核信息的语音信息；S5、根据接收到的所述语音信息对所述坐席进行声纹登录验证，并返回验证结果。
本申请的积极进步效果在于：本申请通过坐席身份和声纹双重验证的登录方式，确保了业务系统登录的安全性；同时，还通过加入均速逐字变色提 示跟读功能，用于确保坐席每次录入时尽可能保持一致的速度进行跟读，进而提高声纹登录验证的准确性。
附图说明
图1示出了本申请电子装置一实施例的硬件架构示意图；
图2示出了本申请电子装置中基于声纹识别的坐席登录系统第一实施例的程序模块示意图；
图3示出了本申请电子装置中基于声纹识别的坐席登录系统第二实施例的程序模块示意图；
图4示出了本申请电子装置中基于声纹识别的坐席登录系统第三实施例中所述身份验证模块的程序模块示意图；
图5示出了本申请电子装置中基于声纹识别的坐席登录系统第四实施例中所述声纹比对模块的程序模块示意图；
图6示出了本申请基于声纹识别的坐席登录方法一实施例的流程图；
图7示出了本申请基于声纹识别的坐席登录方法另一实施例的流程图；
图8示出了本申请基于声纹识别的坐席登录方法又一实施例中注册坐席信息库的构建的流程图；
图9示出了本申请基于声纹识别的坐席登录方法进一步的实施例中注册坐席信息库的构建的流程图。
具体实施方式
下面通过实施例的方式进一步说明本申请，但并不因此将本申请限制在所述的实施例范围之中。
首先，本申请提出了一种电子装置。
参阅图1所示，是本申请电子装置一实施例的硬件架构示意图。本实施例中，所述电子装置1是一种能够按照事先设定或者存储的指令，自动进行 数值计算和/或信息处理的设备。例如，可以是智能手机、平板电脑、笔记本电脑、台式计算机、机架式服务器、刀片式服务器、塔式服务器或机柜式服务器(包括独立的服务器，或者多个服务器所组成的服务器集群)等。如图所示，所述电子装置2至少包括，但不限于，可通过系统总线相互通信连接存储器21、处理器22、网络接口23、以及基于声纹识别的坐席登录系统20。其中：
所述存储器21至少包括一种类型的计算机可读存储介质，所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，所述存储器21可以是所述电子装置2的内部存储单元，例如该电子装置2的硬盘或内存。在另一些实施例中，所述存储器21也可以是所述电子装置2的外部存储设备，例如该电子装置2上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。当然，所述存储器21还可以既包括所述电子装置2的内部存储单元也包括其外部存储设备。本实施例中，所述存储器21通常用于存储安装于所述电子装置2的操作系统和各类应用软件，例如所述基于声纹识别的坐席登录系统20的程序代码等。此外，所述存储器21还可以用于暂时地存储已经输出或者将要输出的各类数据。
所述处理器22在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器22通常用于控制所述电子装置2的总体操作，例如执行与所述电子装置2进行数据交互或者通信相关的控制和处理等。本实施例中，所述处理器22用于运行所述存储器21中存储的程序代码或者处理数据，例如运行所述的基于声纹识别的坐席登录系统20等。
所述网络接口23可包括无线网络接口或有线网络接口，该网络接口23通常用于在所述电子装置2与其他电子装置之间建立通信连接。例如，所述网络接口23用于通过网络将所述电子装置2与外部终端相连，在所述电子装置2与外部终端之间的建立数据传输通道和通信连接等。所述网络可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯系统(Global System of Mobile communication，GSM)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。
需要指出的是，图1仅示出了具有组件21-23的电子装置2，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
在本实施例中，存储于存储器21中的所述基于声纹识别的坐席登录系统20可以被分割为一个或者多个程序模块，所述一个或者多个程序模块被存储于存储器21中，并可由一个或多个处理器(本实施例为处理器22)所执行，以完成本申请。
例如，图2示出了所述基于声纹识别的坐席登录系统20第一实施例的程序模块示意图，该实施例中，所述基于声纹识别的坐席登录系统20可以被分割为身份输入模块201、身份验证模块202、随机信息生成模块203、跟读提示模块204、声音输入模块205和声纹比对模块206。以下描述将具体介绍所述程序模块201-206的具体功能。
所述身份输入模块201，用于接收包含有识别坐席身份的唯一识别信息的坐席的登录请求信息；
所述身份验证模块202，用于根据所述唯一识别信息验证所述坐席是否为注册坐席，并返回验证结果；
所述随机信息生成模块203，用于在身份验证通过后，随机生成身份复核信息并显示；
所述跟读提示模块204，用于使显示的所述身份复核信息均速逐字变色，以提示所述坐席以均速阅读所述身份复核信息；
所述声音输入模块205，用于接收所述坐席阅读所述身份复核信息的声音信息；
所述声纹比对模块206，用于根据所述声音信息对所述坐席进行声纹登录验证，并返回验证结果。
本实施例中所述基于声纹识别的坐席登录系统20的使用，有利于有序管理坐席。下面以坐席使用该系统登录坐席系统加以具体说明：
1、坐席点击业务系统，首先进入的是坐席登录系统，弹出第一登录页面用于输入坐席的唯一识别信息，这里的唯一识别信息可以是坐席的工号，以下步骤均以工号为例做说明；系统接收到该工号后，将该工号和该工位所固有的信息及其他信息组成登录请求信息后进行发送。
2、根据登录请求信息中包含的工号判断该工号所代表的坐席是否为注册坐席；具体为，判断该工号是否与注册坐席信息库预设的工号中的其中一个相同；如果在注册坐席信息库找到与该工号相同的预设工号，则返回代表该坐席为注册坐席的比对结果；否则，结束登录。
3、根据确定坐席为注册坐席的比对结果，弹出第二登录页面，该第二登录页面上显示有随机生成的一串身份复核信息，可以是一串数字、字母、文字或三种的任意组合。
4、坐席根据匀速逐字变色提示读出显示的一串身份复核信息，同时系统录下坐席跟读的语音信息。
5、从录下的语音信息中提取出其中的声纹信息，并调出预设在注册坐席信息库中与该坐席的工号相关联的声纹样本。
6、将声纹信息与调出的声纹样本进行匹配，只要两者达到一定程度的匹配，即判断该坐席为输入的工号所代表的坐席本人，通过声纹登录验证，允许该坐席进入业务系统继续操作。
又例如，图3示出了所述基于声纹识别的坐席登录系统20第二实施例的程序模块示意图，该实施例中，所述基于声纹识别的坐席登录系统20还可以被分割为身份输入模块201、身份验证模块202、随机信息生成模块203、跟读提示模块204、声音输入模块205、声纹比对模块206、校验码生成模块207、校验码输入模块208和校验码验证模块209。
其中，程序模块201-206所实现的功能同前述第一实施例，此处不再详述；除此以外，程序模块207-209所实现的功能如下：
所述校验码生成模块207，用于在声纹登录验证失败后，随机生成校验码发送至预设的所述坐席的邮箱或手机端；
所述校验码输入模块208，用于接收坐席输入的校验码；
所述校验码验证模块209，用于对接收到的校验码进行校验，并返回校验结果。
下面特别针对坐席使用该系统登录坐席系统失败后加以具体说明：
接上例中的1-6；
7、在未通过声纹登录验证后，系统自动随机生成校验码发送至预设在注册坐席信息库中与该坐席的工号相关联的邮箱或者手机上。
8、坐席输入收到的校验码，系统将接收到的校验码与发送给该坐席的校验码进行比对，完全一致则表示校验码验证通过，允许该坐席进入业务系统继续操作；若系统接收到的校验码与发送给该坐席的校验码两者有任一一位校验码不一致，则表示校验码验证未通过，结束登录。
另例如，图4示出了所述基于声纹识别的坐席登录系统20第三实施例中身份验证模块202的程序模块示意图，该实施例中，所述基于声纹识别的坐席登录系统20在前述第二实施例的基础上，将身份验证模块202进一步分割为信息截取子模块2021和身份识别子模块2022。
其中，程序模块2021-2022所实现的功能如下：
所述信息截取子模块21，用于截取包含在所述登录请求信息中的所述唯 一识别信息；
所述身份识别子模块22，用于将所述唯一识别信息与预设在注册坐席信息库中的坐席信息进行一一比对，并返回比对结果。
再例如，图5示出了所述基于声纹识别的坐席登录系统20第三实施例中声纹比对模块206的程序模块示意图，该实施例中，所述基于声纹识别的坐席登录系统20在前述第二实施例的基础上，将声纹比对模块206进一步分割为声纹提取子模块2061、声纹调用子模块2062和声纹比对子模块2063。
其中，程序模块2061-2063所实现的功能如下：
所述声纹提取子模块2061，用于从所述声音信息中提取声纹信息；
所述声纹调用子模块2062，用于从注册坐席信息库中查找出与所述唯一识别信息相同的坐席信息下关联的声纹样本并调出；
所述声纹比对子模块2063，用于将所述声纹信息与调出的所述声纹样本进行比对，并返回比对结果。
其次，本申请提出一种基于声纹识别的坐席登录方法。
在一实施例中，如图6所示，所述的基于声纹识别的坐席登录方法包括如下步骤：
S1、接收坐席发起的登录请求信息，所述登录请求信息中包含有识别坐席身份的唯一识别信息。
举例来说，将本申请实施例的基于声纹识别的坐席登录方法应用于业务登录系统中，当坐席打开业务系统准备登录时，需要在业务系统的坐席端输入账号，该账号转换成登录请求信息发送至业务登录系统。所述账号转换成登录请求信息时，根据转换规则，转换后的登录请求信息中的固定位置的部分信息为用于识别坐席身份的唯一识别信息，这里可以假设为登录请求信息的第5位至第10位组成的字符串为唯一识别信息。
S2、通过所述唯一识别信息验证所述坐席是否为注册坐席，若是则执行步骤S3。
具体地，验证是否为注册坐席可包括以下步骤：
S21、截取所述登录请求信息中识别所述坐席身份的唯一识别信息。
接上例，截取登录请求信息中第5位至第10位组成的一个长度为6位的字符串。
S22、将所述唯一识别信息与预设在注册坐席信息库中的坐席信息进行一一比对。
将前述的表示唯一识别信息的长度为6位的字符串与预设在注册坐席信息库中的坐席信息一一比对，这里所述坐席信息的长度与所述唯一识别信息的长度保持一致，本实施例中假设唯一识别信息为长度为6位的字符串，因而所述坐席信息的长度也必然假设为6位。
S23、若存在匹配项，则通过验证并执行步骤S3。
所述比对结果有两种：当唯一识别信息和注册坐席信息库中任意一个坐席信息完全一致时，返回表示坐席身份验证通过的字符，这里假设为1，并且停止比对；当唯一识别信息与注册坐席信息库中所有的坐席信息一一比对完成，仍没有找到与该唯一识别信息完全一致的坐席信息时，返回表示坐席身份验证不通过的字符，这里假设为0。只有当比对结果为1时，才执行步骤S3，当比对结果为0时，结束登录。
S3、随机生成身份复核信息提供至所述坐席，并通过均速逐字变色提示所述坐席阅读所述身份复核信息。
接上例，当返回结果为0时，表示坐席身份验证不通过，即表示该坐席为本业务系统的非注册坐席，没有权限使用本业务系统，直接结束登录；
当返回结果为1时，表示坐席身份验证通过，即表示该坐席为本业务系统的注册坐席，有权限使用本业务系统，但还需通过声纹识别进行登录验证。由于之前提到，虽然坐席身份验证通过，但有可能实际登录业务系统的坐席为非注册坐席，只是该非注册坐席通过不合理的渠道获得了一个注册坐席的有效账号，若直接通过输入密码验证登录业务系统，很可能造成企业信息泄 露；因而，在验证正在登录的坐席为注册坐席后，系统会随机生成身份复核信息提供至所述坐席，用于坐席的登录验证。
所述身份复核信息可以是若干文字、若干数字或这若干文字和数字的随机组合。具体举例来说，该身份复核信息可以是几个中文字，比如“欢迎登录业务系统”，也可以是几个数字，比如“23059487”，还可以是几个中文字和几个数字的组合，比如“早上好5768”。这里所述文字不限于中文字，可以是英文字母等。
在身份复核信息显示后，等待一段时间，系统自动以一定速度的均速使得所述身份复核信息逐字变色，以提示所述坐席跟着变色的速度逐字匀速阅读所述身份复核信息。通过均速逐字变色，可以有效暗示坐席以字体变色的速度匀速跟读，以便坐席阅读的声音更平稳，方便后续的声纹信息比对。这里的逐字变色的开始时间也可以设计成由坐席自己控制，比如在身份复核信息显示的位置附近，增加开始按钮，待坐席准备好之后，点击开始按钮后，身份复核信息再开始逐字变色。
S4、接收所述坐席阅读所述身份复核信息的语音信息。
接上例，由于采用逐字变色提示跟读的方式，这里接收语音信息的结束时间可以在系统内预设，比如：在身份复核信息的最后一个字变色后的3秒默认完成接收语音信息，自动停止语音信息的接收。当然，接收语音信息的结束与否，也可以由坐席自己决定，只要同前述开始按钮一样，增加结束按钮即可。
S5、根据接收到的所述语音信息对所述坐席进行声纹登录验证。
所述声纹登录验证具备包括以下步骤：
S51、提取所述语音信息中的声纹信息。
所述声纹信息，具体而言就是可以表征一个人特点的特征，因而这里所述的提取声纹信息，就是从接收到的语音信息中提取出可以表征阅读前述身份复核信息的坐席特点的特征。
S52、在注册坐席信息库中查找并调出与所述唯一识别信息匹配的坐席信息下关联的声纹样本。
这里所述声纹样本，是指预设在注册坐席信息库的注册坐席的声纹信息，一个声纹样本关联一个唯一的坐席信息后保存在注册坐席信息库。
S53、将所述声纹信息与S52中调出所述声纹样本进行匹配。
具体而言，就是用当前获取的声纹信息与一个声纹样本进行匹配，该声纹样本属于由与唯一识别信息相同的坐席信息所代表的坐席身份所特有的声纹信息。
S54、如果匹配通过，则判断所述坐席通过登录验证。
接上例，因为调出的声纹样本属于由与唯一识别信息相同的坐席信息所代表的坐席身份所特有的；因此，当声纹信息与所调出的声纹样本相匹配时，则可判断出本次登录业务系统的坐席确实是所述唯一识别信息所代表的坐席本人，进而通过登录验证，允许该坐席进入业务系统继续操作。
在另一实施例中，如图7所示，所述的基于声纹识别的坐席登录方法在前述方法的基础上，还包括在声纹登录验证失败之后的校验码登录验证步骤，具体步骤如下：
S6、在声纹登录验证失败后，随机生成校验码发送至预设的所述坐席的邮箱或手机端。
由于每次通过提取录音中的声纹信息来识别个人的身份信息具有一定的误差，这种误差来自于录音环境或者个人本身声音的变化等，因此声纹验证登录时，并不要求声纹信息和声纹样本两者完全匹配，通常只要达到一定程度的匹配度即可；更有甚者，匹配度达不到预设值时，当前登录的坐席也可能就是与所述唯一识别信息相同的坐席信息所代表的坐席。因此在声纹登录验证失败后，通过增加校验码登录验证来弥补声纹登录验证可能出现的异常。
校验码登录验证是对声纹登录验证的补充，因而只有当进入声纹登录验 证步骤后并且验证失败后才会启动。注册坐席信息库中的坐席信息所关联的信息除了声纹样本以外，还关联有该注册坐席的手机号码或者邮箱或者两者都有。当进入声纹登录验证步骤，也就表示通过唯一识别信息已经确认该坐席为注册坐席，一旦声纹登录验证失败，直接随机生成校验码，发送至与所述唯一识别信息相同的坐席信息所关联的邮箱或手机上。需要说明的是，此处随机生成校验码的时机可以在声纹登录验证失败一次之后，也可以设定为声纹登录验证失败三次后，即给予坐席三次声纹验证的机会。此处校验码的生成也可以由坐席控制，由坐席选择是否需要生成并发送校验码。
S7、接收所述校验码并进行校验；
S8、如果接收到的所述校验码与随机生成的校验码匹配，则判断所述坐席通过登录验证。
具体地，通过将接收到校验码与之前随机生成校验码的进行比对，完全一致则验证通过，允许该坐席进入业务系统继续操作；否则结束登录。
在又一实施例中，如图8所示，所述的基于声纹识别的坐席登录方法在前述一实施例所述方法的基础上，还包括在进入登录验证之前的注册坐席信息库的构建步骤，具体步骤如下：
S01、接收待注册坐席的唯一识别信息，并将所述唯一识别信息作为所述待注册坐席的坐席信息进行暂存；
S02、随机生成一组跟读信息提供至待注册坐席；
S03、至少以一种均速逐字变色提示所述待注册坐席阅读所述跟读信息不少于三次，并暂存该待注册坐席的多次跟读语音信息；
S04、将多次跟读语音信息进行拟合，得到拟合语音信息；
S05、提取所述拟合语音信息中的声纹信息作为声纹样本；
S06、将所述声纹样本与暂存的所述待注册坐席的坐席信息进行关联并保存。
为了在声纹登录验证失败后，还能通过校验码登录验证来作为补充，在 前述又一实施例的基础上，还提出了一个进一步的实施例，如图9所示，所述的基于声纹识别的坐席登录方法在注册坐席信息库的构建时，还包括坐席信息与坐席手机号码和/或邮箱的关联，具体步骤如下：
S01-S04同前述又一实施例；
S05、提取所述拟合语音信息中的声纹信息作为声纹样本暂存；
S06、接收待注册坐席的手机号码和/或邮箱；
S07、将所述声纹样本和手机号码和/或邮箱与暂存的所述待注册坐席的坐席信息进行关联并保存。
此外，本申请一种计算机可读存储介质，该计算机可读存储介质内存储有基于声纹识别的坐席登录系统20，该基于声纹识别的坐席登录系统20可被一个或多个处理器执行时，实现上述基于声纹识别的坐席登录方法或电子装置的操作。
虽然以上描述了本申请的具体实施方式，但是本领域的技术人员应当理解，这仅是举例说明，本申请的保护范围是由所附权利要求书限定的。本领域的技术人员在不背离本申请的原理和实质的前提下，可以对这些实施方式做出多种变更或修改，但这些变更和修改均落入本申请的保护范围。

Claims (14)

  1. 一种基于声纹识别的坐席登录方法，其特征在于，包括如下步骤：
    S1、接收坐席发起的登录请求信息，所述登录请求信息中包含有识别坐席身份的唯一识别信息；
    S2、通过所述唯一识别信息验证所述坐席是否为注册坐席，若是则执行步骤S3；
    S3、随机生成身份复核信息提供至所述坐席，并通过均速逐字变色提示所述坐席阅读所述身份复核信息；
    S4、接收所述坐席阅读所述身份复核信息的语音信息；
    S5、根据接收到的所述语音信息对所述坐席进行声纹登录验证，并返回验证结果。
  2. 根据权利要求1所述的基于声纹识别的坐席登录方法，其特征在于，所述步骤S2具体包括如下子步骤：
    S21、截取所述登录请求信息中识别所述坐席身份的唯一识别信息；
    S22、将所述唯一识别信息与预设在注册坐席信息库中的坐席信息进行一一比对；
    S23、若存在匹配项，则通过验证并执行步骤S3。
  3. 根据权利要求2所述的基于声纹识别的坐席登录方法，其特征在于，所述步骤S5具体包括如下子步骤：
    S51、提取所述语音信息中的声纹信息；
    S52、在注册坐席信息库中查找并调出与所述唯一识别信息匹配的坐席信息下关联的声纹样本；
    S53、将所述声纹信息与S52中调出所述声纹样本进行匹配；
    S54、如果匹配通过，则判断所述坐席通过登录验证。
  4. 根据权利要求2或3所述的基于声纹识别的坐席登录方法，其特征 在于，还包括如下步骤：
    S6、在声纹登录验证失败后，随机生成校验码发送至预设的所述坐席的邮箱或手机端；
    S7、接收所述校验码并进行校验；
    S8、如果接收到的所述校验码与随机生成的校验码匹配，则判断所述坐席通过登录验证。
  5. 根据权利要求2或3所述的一种基于声纹识别的坐席登录方法，其特征在于，所述步骤S1之前还包括：
    S0、构建注册坐席信息库，具体步骤如下：
    S01、接收待注册坐席的唯一识别信息，并将所述唯一识别信息作为所述待注册坐席的坐席信息进行暂存；
    S02、随机生成一组跟读信息提供至待注册坐席；
    S03、至少以一种均速逐字变色提示所述待注册坐席阅读所述跟读信息不少于三次，并暂存该待注册坐席的多次跟读语音信息；
    S04、将多次跟读语音信息进行拟合，得到拟合语音信息；
    S05、提取所述拟合语音信息中的声纹信息作为声纹样本；
    S06、将所述声纹样本与暂存的所述待注册坐席的坐席信息进行关联并保存。
  6. 一种电子装置，包括存储器和处理器，其特征在于，所述存储器上存储有可被所述处理器执行的基于声纹识别的坐席登录系统，所述基于声纹识别的坐席登录系统包括：
    身份输入模块，用于接收包含有识别坐席身份的唯一识别信息的坐席的登录请求信息；
    身份验证模块，用于根据所述唯一识别信息验证所述坐席是否为注册坐席，并返回验证结果；
    随机信息生成模块，用于在身份验证通过后，随机生成身份复核信息并 显示；
    跟读提示模块，用于使显示的所述身份复核信息均速逐字变色，以提示所述坐席以均速阅读所述身份复核信息；
    声音输入模块，用于接收所述坐席阅读所述身份复核信息的声音信息；
    声纹比对模块，用于根据所述声音信息对所述坐席进行声纹登录验证，并返回验证结果。
  7. 根据权利要求6所述的电子装置，其特征在于，所述身份验证模块包括：
    信息截取子模块，用于截取包含在所述登录请求信息中的所述唯一识别信息；
    身份识别子模块，用于将所述唯一识别信息与预设在注册坐席信息库中的坐席信息进行一一比对，并返回比对结果。
  8. 根据权利要求6所述的电子装置，其特征在于，所述声纹比对模块包括：
    声纹提取子模块，用于从所述声音信息中提取声纹信息；
    声纹调用子模块，用于从注册坐席信息库中查找出与所述唯一识别信息相同的坐席信息下关联的声纹样本并调出；
    声纹比对子模块，用于将所述声纹信息与调出的所述声纹样本进行比对，并返回比对结果。
  9. 根据权利要求6-8中任一项所述的电子装置，其特征在于，所述坐席登录系统还包括：
    校验码生成模块，用于在声纹登录验证失败后，随机生成校验码发送至预设的所述坐席的邮箱或手机端；
    校验码输入模块，用于接收坐席输入的校验码；
    校验码验证模块，用于对接收到的校验码进行校验，并返回校验结果。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质 内存储有基于声纹识别的坐席登录系统，所述基于声纹识别的坐席登录系统可被至少一个处理器所执行，以使所述至少一个处理器执行以下步骤：
    S1、接收坐席发起的登录请求信息，所述登录请求信息中包含有识别坐席身份的唯一识别信息；
    S2、通过所述唯一识别信息验证所述坐席是否为注册坐席，若是则执行步骤S3；
    S3、随机生成身份复核信息提供至所述坐席，并通过均速逐字变色提示所述坐席阅读所述身份复核信息；
    S4、接收所述坐席阅读所述身份复核信息的语音信息；
    S5、根据接收到的所述语音信息对所述坐席进行声纹登录验证，并返回验证结果。
  11. 根据权利要求10所述的计算机可读存储介质，其特征在于，所述步骤S2具体包括如下子步骤：
    S21、截取所述登录请求信息中识别所述坐席身份的唯一识别信息；
    S22、将所述唯一识别信息与预设在注册坐席信息库中的坐席信息进行一一比对；
    S23、若存在匹配项，则通过验证并执行步骤S3。
  12. 根据权利要求11所述的计算机可读存储介质，其特征在于，所述步骤S5具体包括如下子步骤：
    S51、提取所述语音信息中的声纹信息；
    S52、在注册坐席信息库中查找并调出与所述唯一识别信息匹配的坐席信息下关联的声纹样本；
    S53、将所述声纹信息与S52中调出所述声纹样本进行匹配；
    S54、如果匹配通过，则判断所述坐席通过登录验证。
  13. 根据权利要求11或12所述的计算机可读存储介质，其特征在于，所述至少一个处理器还执行以下步骤：
    S6、在声纹登录验证失败后，随机生成校验码发送至预设的所述坐席的邮箱或手机端；
    S7、接收所述校验码并进行校验；
    S8、如果接收到的所述校验码与随机生成的校验码匹配，则判断所述坐席通过登录验证。
  14. 根据权利要求11或12所述的计算机可读存储介质，其特征在于，所述步骤S1之前还包括：
    S0、构建注册坐席信息库，具体步骤如下：
    S01、接收待注册坐席的唯一识别信息，并将所述唯一识别信息作为所述待注册坐席的坐席信息进行暂存；
    S02、随机生成一组跟读信息提供至待注册坐席；
    S03、至少以一种均速逐字变色提示所述待注册坐席阅读所述跟读信息不少于三次，并暂存该待注册坐席的多次跟读语音信息；
    S04、将多次跟读语音信息进行拟合，得到拟合语音信息；
    S05、提取所述拟合语音信息中的声纹信息作为声纹样本；
    S06、将所述声纹样本与暂存的所述待注册坐席的坐席信息进行关联并保存。
PCT/CN2018/077375 2017-09-11 2018-02-27 基于声纹识别的坐席登录方法、电子装置及存储介质 WO2019047487A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
SG11201811498QA SG11201811498QA (en) 2017-09-11 2018-02-27 Agent login method, electronic device and storage medium based on voiceprint identification
US16/338,957 US20210312023A1 (en) 2017-09-11 2018-02-27 Agent Login Method, Electronic Device And Storage Medium Based On Voiceprint Identification
JP2018561019A JP2019535025A (ja) 2017-09-11 2018-02-27 声紋識別によるエージェントログイン方法、電子装置及び記憶媒体

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710814313.4 2017-09-11
CN201710814313.4A CN108512664A (zh) 2017-09-11 2017-09-11 基于声纹识别的坐席登录方法、电子装置及存储介质

Publications (1)

Publication Number Publication Date
WO2019047487A1 true WO2019047487A1 (zh) 2019-03-14

Family

ID=63374497

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/077375 WO2019047487A1 (zh) 2017-09-11 2018-02-27 基于声纹识别的坐席登录方法、电子装置及存储介质

Country Status (5)

Country Link
US (1) US20210312023A1 (zh)
JP (1) JP2019535025A (zh)
CN (1) CN108512664A (zh)
SG (1) SG11201811498QA (zh)
WO (1) WO2019047487A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111856399A (zh) * 2019-04-26 2020-10-30 北京嘀嘀无限科技发展有限公司 基于声音的定位识别方法、装置、电子设备及存储介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109346085B (zh) * 2018-10-29 2021-09-28 合肥赛为智能有限公司 一种基于声纹识别的监狱监管平台
CN111243605A (zh) * 2020-01-13 2020-06-05 北京三快在线科技有限公司 业务处理方法、装置、设备及存储介质
CN112332990B (zh) * 2020-09-09 2023-05-12 深圳市奥拓电子股份有限公司 一种指挥调度坐席的安全控制方法、装置及存储介质
CN116597845B (zh) * 2023-07-14 2023-10-10 深圳奥联信息安全技术有限公司 一种随机式声纹验证系统及方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103986725A (zh) * 2014-05-29 2014-08-13 中国农业银行股份有限公司 一种客户端、服务器端以及身份认证系统和方法
CN104036780A (zh) * 2013-03-05 2014-09-10 阿里巴巴集团控股有限公司 一种人机识别方法及系统
CN107104803A (zh) * 2017-03-31 2017-08-29 清华大学 一种基于数字口令与声纹联合确认的用户身份验证方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10173644A (ja) * 1996-12-11 1998-06-26 Nippon Telegr & Teleph Corp <Ntt> 本人認証方法
JP2000250861A (ja) * 1999-02-26 2000-09-14 Nec Corp 非接触式ｉｃカードログインシステム及びそのログイン方法
WO2006027844A1 (ja) * 2004-09-10 2006-03-16 Mitsubishi Denki Kabushiki Kaisha 話者照合装置
WO2015194017A1 (ja) * 2014-06-19 2015-12-23 日立マクセル株式会社 ウェアラブル装置および認証方法
JP6561345B2 (ja) * 2015-01-23 2019-08-21 株式会社日本総合研究所 認証サーバ、声紋認証システム、及び声紋認証方法
CN105185379B (zh) * 2015-06-17 2017-08-18 百度在线网络技术（北京）有限公司 声纹认证方法和装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104036780A (zh) * 2013-03-05 2014-09-10 阿里巴巴集团控股有限公司 一种人机识别方法及系统
CN103986725A (zh) * 2014-05-29 2014-08-13 中国农业银行股份有限公司 一种客户端、服务器端以及身份认证系统和方法
CN107104803A (zh) * 2017-03-31 2017-08-29 清华大学 一种基于数字口令与声纹联合确认的用户身份验证方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111856399A (zh) * 2019-04-26 2020-10-30 北京嘀嘀无限科技发展有限公司 基于声音的定位识别方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN108512664A (zh) 2018-09-07
SG11201811498QA (en) 2019-04-29
US20210312023A1 (en) 2021-10-07
JP2019535025A (ja) 2019-12-05

Similar Documents

Publication Publication Date Title
WO2019047487A1 (zh) 基于声纹识别的坐席登录方法、电子装置及存储介质
US11816199B1 (en) Efficient logon
CN109474578B (zh) 报文消息校验方法、装置、计算机设备和存储介质
CN103546877B (zh) 一种获取并输入内容码的方法、系统和移动终端
US10812479B2 (en) Authenticating a user via multiple biometric inputs
US11709921B1 (en) Quick-logon for computing device
EP3211825B1 (en) Trusted terminal verification method and apparatus
WO2020258655A1 (zh) 数据校验方法、装置、计算机设备和存储介质
CN111343162B (zh) 系统安全登录方法、装置、介质及电子设备
KR20150014951A (ko) 소셜 네트워크들에 대한 사용자-기반 식별 시스템
CN110334144B (zh) 报文展示方法、装置、计算机设备及存储介质
US9589122B2 (en) Operation processing method and device
WO2020181809A1 (zh) 基于接口校验的数据处理的方法、系统和计算机设备
CN109089231B (zh) 验证码短信的转发方法、装置、服务器和介质
CN112528262A (zh) 基于令牌的应用程序访问方法、装置、介质及电子设备
WO2018233137A1 (zh) 电子装置、进线身份识别方法和计算机可读存储介质
US20190068584A1 (en) Verification information processing method and device
US20200112560A1 (en) System for improved identification and authentication
US10735398B1 (en) Rolling code authentication techniques
US20210042150A1 (en) Method-call-chain tracking method, electronic device, and computer readable storage medium
WO2020206906A1 (zh) 注册信息处理方法、装置、计算机设备和存储介质
US20190370688A1 (en) Machine learning for isolated data sets
US10855677B2 (en) Voice-based verification for multi-factor authentication challenges
US10778673B2 (en) Methods for randomized multi-factor authentication with biometrics and devices thereof
CN110113346B (zh) 一种网络验证方法、用户终端及服务器

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2018561019

Country of ref document: JP

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18854295

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 23/09/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18854295

Country of ref document: EP

Kind code of ref document: A1